Changes between Initial Version and Version 2 of Ticket #308
- Timestamp:
- 10/31/08 19:47:50 (5 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Ticket #308
- Property status changed from new to assigned
-
Ticket #308 – description
initial v2 1 An example formula that uses the loess function is: 2 3 {{{ 4 presence ~ lo(mlfor) + lo(dfor2) + lo(preyall) + lo(insolindex) 5 }}} 6 1 7 The gam package's predict.gam function includes a parameter called na.action. The documentation for this parameter states "function determining what should be done with missing values in 'newdata'. The default is to predict 'NA'." In other words, if one of the predictors is NA, the predicted response will be NA. This does not seem to be true. Instead you get this error (from the MGET tool): 2 8 … … 38 44 39 45 To work around this, MGET should just not pass NA values to predict.gam. 46 47 Thanks to Dave LaPlante for reporting this problem.
